dc.contributor.author |
Van der Walt, CM
|
|
dc.contributor.author |
Barnard, E
|
|
dc.date.accessioned |
2014-02-26T06:46:24Z |
|
dc.date.available |
2014-02-26T06:46:24Z |
|
dc.date.issued |
2013-12 |
|
dc.identifier.citation |
Van der Walt, C.M and Barnard, E. 2014. Kernel bandwidth estimation for non-parametric density estimation: a comparative study. In: Proceedings of the Twenty-Fourth Annual Symposium of the Pattern Recognition Association of South Africa, Johannesburg, South Africa, 3 December 2013 |
en_US |
dc.identifier.isbn |
978-0-86970-771-5 |
|
dc.identifier.uri |
http://www.prasa.org/proceedings/2013/prasa2013-16.pdf
|
|
dc.identifier.uri |
http://hdl.handle.net/10204/7236
|
|
dc.description |
Proceedings of the Twenty-Fourth Annual Symposium of the Pattern Recognition Association of South Africa, Johannesburg, South Africa, 3 December 2013 |
en_US |
dc.description.abstract |
We investigate the performance of conventional bandwidth estimators for non-parametric kernel density estimation on a number of representative pattern-recognition tasks, to gain a better understanding of the behaviour of these estimators in high-dimensional spaces. We show that there are several regularities in the relative performance of conventional kernel bandwidth estimators across different tasks and dimensionalities. In particular, we find that the Silverman rule-of-thumb and maximal-smoothing principle estimators consistently perform competitively on most tasks and dimensions for the datasets considered. |
en_US |
dc.language.iso |
en |
en_US |
dc.publisher |
PRASA 2013 Proceedings |
en_US |
dc.relation.ispartofseries |
Workflow;12172 |
|
dc.subject |
Non-parametric density estimation |
en_US |
dc.subject |
Kernel density estimation |
en_US |
dc.subject |
Kernel bandwidth estimation |
en_US |
dc.subject |
Pattern recognition |
en_US |
dc.title |
Kernel bandwidth estimation for non-parametric density estimation: a comparative study |
en_US |
dc.type |
Conference Presentation |
en_US |
dc.identifier.apacitation |
Van der Walt, C., & Barnard, E. (2013). Kernel bandwidth estimation for non-parametric density estimation: a comparative study. PRASA 2013 Proceedings. http://hdl.handle.net/10204/7236 |
en_ZA |
dc.identifier.chicagocitation |
Van der Walt, CM, and E Barnard. "Kernel bandwidth estimation for non-parametric density estimation: a comparative study." (2013): http://hdl.handle.net/10204/7236 |
en_ZA |
dc.identifier.vancouvercitation |
Van der Walt C, Barnard E, Kernel bandwidth estimation for non-parametric density estimation: a comparative study; PRASA 2013 Proceedings; 2013. http://hdl.handle.net/10204/7236 . |
en_ZA |
dc.identifier.ris |
TY - Conference Presentation
AU - Van der Walt, CM
AU - Barnard, E
AB - We investigate the performance of conventional bandwidth estimators for non-parametric kernel density estimation on a number of representative pattern-recognition tasks, to gain a better understanding of the behaviour of these estimators in high-dimensional spaces. We show that there are several regularities in the relative performance of conventional kernel bandwidth estimators across different tasks and dimensionalities. In particular, we find that the Silverman rule-of-thumb and maximal-smoothing principle estimators consistently perform competitively on most tasks and dimensions for the datasets considered.
DA - 2013-12
DB - ResearchSpace
DP - CSIR
KW - Non-parametric density estimation
KW - Kernel density estimation
KW - Kernel bandwidth estimation
KW - Pattern recognition
LK - https://researchspace.csir.co.za
PY - 2013
SM - 978-0-86970-771-5
T1 - Kernel bandwidth estimation for non-parametric density estimation: a comparative study
TI - Kernel bandwidth estimation for non-parametric density estimation: a comparative study
UR - http://hdl.handle.net/10204/7236
ER -
|
en_ZA |